Showing papers by "Georgios Paltoglou published in 2011"

Sentiment in Twitter events

Abstract: The microblogging site Twitter generates a constant stream of communication, some of which concerns events of general interest. An analysis of Twitter may, therefore, give insights into why particular events resonate with the population. This article reports a study of a month of English Twitter posts, assessing whether popular events are typically associated with increases in sentiment strength, as seems intuitively likely. Using the top 30 events, determined by a measure of relative increase in (general) term usage, the results give strong evidence that popular events are normally associated with increases in negative sentiment strength and some evidence that peaks of interest in events have stronger positive sentiment than the time before the peak. It seems that many positive events, such as the Oscars, are capable of generating increased negative sentiment in reaction to them. Nevertheless, the surprisingly small average change in sentiment associated with popular events (typically 1% and only 6% for Tiger Woods' confessions) is consistent with events affording posters opportunities to satisfy pre-existing personal goals more often than eliciting instinctive reactions. © 2011 Wiley Periodicals, Inc.

Collective emotions online and their influence on community life.

Abstract: Background E-communities, social groups interacting online, have recently become an object of interdisciplinary research. As with face-to-face meetings, Internet exchanges may not only include factual information but also emotional information – how participants feel about the subject discussed or other group members. Emotions in turn are known to be important in affecting interaction partners in offline communication in many ways. Could emotions in Internet exchanges affect others and systematically influence quantitative and qualitative aspects of the trajectory of e-communities? The development of automatic sentiment analysis has made large scale emotion detection and analysis possible using text messages collected from the web. However, it is not clear if emotions in e-communities primarily derive from individual group members' personalities or if they result from intra-group interactions, and whether they influence group activities. Methodology/Principal Findings Here, for the first time, we show the collective character of affective phenomena on a large scale as observed in four million posts downloaded from Blogs, Digg and BBC forums. To test whether the emotions of a community member may influence the emotions of others, posts were grouped into clusters of messages with similar emotional valences. The frequency of long clusters was much higher than it would be if emotions occurred at random. Distributions for cluster lengths can be explained by preferential processes because conditional probabilities for consecutive messages grow as a power law with cluster length. For BBC forum threads, average discussion lengths were higher for larger values of absolute average emotional valence in the first ten comments and the average amount of emotion in messages fell during discussions. Conclusions/Significance Overall, our results prove that collective emotional states can be created and modulated via Internet communication and that emotional expressiveness is the fuel that sustains some e-communities.

Negative emotions boost user activity at BBC forum

Abstract: We present an empirical study of user activity in online BBC discussion forums, measured by the number of posts written by individual debaters and the average sentiment of these posts. Nearly 2.5 million posts from over 18 thousand users were investigated. Scale-free distributions were observed for activity in individual discussion threads as well as for overall activity. The number of unique users in a thread normalized by the thread length decays with thread length, suggesting that thread life is sustained by mutual discussions rather than by independent comments. Automatic sentiment analysis shows that most posts contain negative emotions and the most active users in individual threads express predominantly negative sentiments. It follows that the average emotion of longer threads is more negative and that threads can be sustained by negative comments. An agent-based computer simulation model has been used to reproduce several essential characteristics of the analyzed system. The model stresses the role of discussions between users, especially emotionally laden quarrels between supporters of opposite opinions, and represents many observed statistics of the forum.

Quantitative analysis of bloggers' collective behavior powered by emotions

Abstract: Large-scale data resulting from users' online interactions provide the ultimate source of information to study emergent social phenomena on the Web. From individual actions of users to observable collective behaviors, different mechanisms involving emotions expressed in the posted text play a role. Here we combine approaches of statistical physics with machine-learning methods of text analysis to study the emergence of emotional behavior among Web users. Mapping the high-resolution data from digg.com onto bipartite networks of users and their comments onto posted stories, we identify user communities centered around certain popular posts and determine emotional contents of the related comments by the emotion classifier developed for this type of text. Applied over different time periods, this framework reveals strong correlations between the excess of negative emotions and the evolution of communities. We observe avalanches of emotional comments exhibiting significant self-organized critical behavior and temporal correlations. To explore the robustness of these critical states, we design a network-automaton model on realistic network connections and several control parameters, which can be inferred from the dataset. Dissemination of emotions by a small fraction of very active users appears to critically tune the collective states.

No peanut! Affective Cues for the Virtual Bartender

Abstract: The aim of this paper are threefold: it explores methods for the detection of affective states in text, it presents the usage of such affective cues in a conversational system and it evaluates its effectiveness in a virtual reality setting. Valence and arousal values, used for generating facial expressions of users’ avatars, are also incorporated into the dialog, helping to bridge the gap between textual and visual modalities. The system is evaluated in terms of its ability to: i) generate a realistic dialog, ii) create an enjoyable chatting experience, and iii) establish an emotional connection with participants. Results show that user ratings for the conversational agent match those obtained in a Wizard of Oz setting

Emotional Analysis of Blogs and Forums Data

Abstract: We perform a statistical analysis of emotionally annotated comments in two large online datasets, examining chains of consecutive posts in the discussions. Using comparisons with randomised data we show that there is a high level of correlation for the emotional content of messages.

Affect Bartender — Affective cues and their application in a conversational agent

Abstract: This paper presents methods for the detection of textual expressions of users' affective states and explores an application of these affective cues in a conversational system — Affect Bartender. We also describe the architecture of the system, core system components and a range of developed communication interfaces. The application of the described methods is illustrated with examples of dialogs conducted with experiment participants in a Virtual Reality setting.

An interdisciplinary VR-architecture for 3D chatting with non-verbal communication

Abstract: The communication between avatar and agent has already been treated from different but specialized perspectives. In contrast, this paper gives a balanced view of every key architectural aspect: from text analysis to computer graphics, the chatting system and the emotional model. Non-verbal communication, such as facial expression, gaze, or head orientation is crucial to simulate realistic behavior, but is still an aspect neglected in the simulation of virtual societies. In response, this paper aims to present the necessary modularity to allow virtual humans (VH) conversation with consistent facial expression -either between two users through their avatars, between an avatar and an agent, or even between an avatar and a Wizard of Oz. We believe such an approach is particularly suitable for the design and implementation of applications involving VHs interaction in virtual worlds. To this end, three key features are needed to design and implement this system entitled 3D-emoChatting. First, a global architecture that combines components from several research fields. Second, a real-time analysis and management of emotions that allows interactive dialogues with non-verbal communication. Third, a model of a virtual emotional mind called emoMind that allows to simulate individual emotional characteristics. To conclude the paper, we briefly present the basic description of a user-test which is beyond the scope of the present paper.

Modeling information sources as integrals for effective and efficient source selection

Abstract: In this paper, a new source selection algorithm for uncooperative distributed information retrieval environments is presented. The algorithm functions by modeling each information source as an integral, using the relevance score and the intra-collection position of its sampled documents in reference to a centralized sample index and selects the collections that cover the largest area in the rank-relevance space. Based on the above novel metric, the algorithm explicitly focuses on addressing the two goals of source selection; high-recall, which is important for source recommendation applications and high-precision which is important for distributed information retrieval, aiming to produce a high-precision final merged list. For the latter goal in particular, the new approach steps away from the usual practice of DIR systems of explicitly declaring the number of collections that must be queried and instead focuses solely on the number of retrieved documents in the final merged list, dynamically calculating the number of collections that are selected and the number of documents requested from each. The algorithm is tested in a wide range of testbeds in both recall and precision-oriented settings and its effectiveness is found to be equal or better than other state-of-the-art algorithms.

Sentiment inTwitter Events

Abstract: The microblogging site Twitter generates a constant stream of communication, some of which concerns events of general interest. An analysis of Twitter may, therefore, give insights into why particular events resonate with the population. This article reports a study of a month of English Twitter posts, assessing whether popular events are typically associated with increases in sentiment strength, as seems intuitively likely. Using the top 30 events, determined by a measure of relative increase in (general) term usage, the results give strong evidence that popular events are normally associated with increases in negative sentiment strength and some evidence that peaks of interest in events have stronger positivesentimentthanthetimebeforethepeak.Itseems that many positive events, such as the Oscars, are capable of generating increased negative sentiment in reactiontothem.Nevertheless,thesurprisinglysmallaverage change in sentiment associated with popular events (typically 1% and only 6% for Tiger Woods’ confessions) is consistent with events affording posters opportunities to satisfy pre-existing personal goals more often than eliciting instinctive reactions.

University of Wolverhampton at the TREC 2011 Microblog Track.

Abstract: In this report we discuss the experiments we conducted at the University of Wolverhampton for the Microblog Track at TREC-2011. As this was the first time we participated in TREC and the particular task presents some unique challenges we initially focused on properly analyzing and indexing the new Tweets2011 Corpus. We experimented with the effects that some standard IR techniques, such as query expansion and proximity models have in this setting. Initial results indicated that both techniques provide small increases in precision, but more experiments are needed for final conclusions to be reached. Lastly, we experimented with using the page that a tweet links to as part of the tweet. The results were particularly low, indicating a potential error in the indexing process or a natural outcome, due to the increased length of the combined documents. More research into answering the issue is underway.